You’re out of free articles.
Log in
To continue reading, log in to your account.
Create a Free Account
To unlock more free articles, please create a free account.
Sign In or Create an Account.
By continuing, you agree to the Terms of Service and acknowledge our Privacy Policy
Welcome to Heatmap
Thank you for registering with Heatmap. Climate change is one of the greatest challenges of our lives, a force reshaping our economy, our politics, and our culture. We hope to be your trusted, friendly, and insightful guide to that transformation. Please enjoy your free articles. You can check your profile here .
subscribe to get Unlimited access
Offer for a Heatmap News Unlimited Access subscription; please note that your subscription will renew automatically unless you cancel prior to renewal. Cancellation takes effect at the end of your current billing period. We will let you know in advance of any price changes. Taxes may apply. Offer terms are subject to change.
Subscribe to get unlimited Access
Hey, you are out of free articles but you are only a few clicks away from full access. Subscribe below and take advantage of our introductory offer.
subscribe to get Unlimited access
Offer for a Heatmap News Unlimited Access subscription; please note that your subscription will renew automatically unless you cancel prior to renewal. Cancellation takes effect at the end of your current billing period. We will let you know in advance of any price changes. Taxes may apply. Offer terms are subject to change.
Create Your Account
Please Enter Your Password
Forgot your password?
Please enter the email address you use for your account so we can send you a link to reset your password:
AI has already changed weather forecasting forever.
It’s been a wild few years in the typically tedious world of weather predictions. For decades, forecasts have been improving at a slow and steady pace — the standard metric is that every decade of development leads to a one-day improvement in lead time. So today, our four-day forecasts are about as accurate as a one-day forecast was 30 years ago. Whoop-de-do.
Now thanks to advances in (you guessed it) artificial intelligence, things are moving much more rapidly. AI-based weather models from tech giants such as Google DeepMind, Huawei, and Nvidia are now consistently beating the standard physics-based models for the first time. And it’s not just the big names getting into the game — earlier this year, the 27-person team at Palo Alto-based startup Windborne one-upped DeepMind to become the world’s most accurate weather forecaster.
“What we’ve seen for some metrics is just the deployment of an AI-based emulator can gain us a day in lead time relative to traditional models,” Daryl Kleist, who works on weather model development at the National Oceanic and Atmospheric Administration, told me. That is, today’s two-day forecast could be as accurate as last year’s one-day forecast.
All weather models start by taking in data about current weather conditions. But from there, how they make predictions varies wildly. Traditional weather models like the ones NOAA and the European Centre for Medium-Range Weather Forecasts use rely on complex atmospheric equations based on the laws of physics to predict future weather patterns. AI models, on the other hand, are trained on decades of prior weather data, using the past to predict what will come next.
Kleist told me he certainly saw AI-based weather forecasting coming, but the speed at which it’s arriving and the degree to which these models are improving has been head-spinning. “There's papers coming out in preprints almost on a bi-weekly basis. And the amount of skill they've been able to gain by fine tuning these things and taking it a step further has been shocking, frankly,” he told me.
So what changed? As the world has seen with the advent of large language models like ChatGPT, AI architecture has gotten much more powerful, period. The weather models themselves are also in a cycle of continuous improvement — as more open source weather data becomes available, models can be retrained. Plus, the cost of computing power has come way down, making it possible for a small company like Windborne to train its industry-leading model.
Founded by a team of Stanford students and graduates in 2019, Windborne used off-the-shelf Nvidia gaming GPUs to train its AI model, called WeatherMesh — something the company’s CEO and co-founder, John Dean, told me wouldn’t have been possible five years ago. The company also operates its own fleet of advanced weather balloons, which gather data from traditionally difficult-to-access areas.
Standard weather balloons without onboard navigation typically ascend too high, overinflate, and pop within a matter of hours (thus becoming environmental waste, sad!). Since it’s expensive to do launches at sea or in areas without much infrastructure, there’s vast expanses of the globe where most balloons aren’t gathering any data at all.
Satellites can help, of course. But because they’re so far away, they can’t provide the same degree of fidelity. With modern electronics, though, Windborne found it could create a balloon that autonomously changes altitude and navigates to its intended target by venting gas to descend and dropping ballast to ascend.
“We basically took a lot of the innovations that lead to smartphones, global satellite communications, all of the last 20 years of progress in consumer electronics and other things and applied that to balloons,” Dean told me. In the past, the electronics needed to control Windborne’s system would have been too heavy — the balloon wouldn’t have gotten off the ground. But with today’s tiny tech, they can stay aloft for up to 40 days. Eventually, the company aims to recover and reuse at least 80% of its balloons.
The longer airtime allows Windborne to do more with less. While globally there are more than 1,000 conventional weather balloons launched every day, Dean told me, “We collect roughly on the order of 10% or 20% of the data that NOAA collects every day with only 100 launches per month.” In fact, NOAA is a customer of the startup — Windborne already makes millions in revenue selling its weather balloon data to various government agencies.
Now, with a potentially historic hurricane season ramping up, Windborne has the potential to provide the most accurate data on when and where a storm will touch down.
Earlier this year, the company used WeatherMesh to run a case study on Hurricane Ian, the Category 5 storm that hit Florida in September 2022, leading to over 150 fatalities and $112 billion in damages. Using only weather data that was publicly available at the time, the company looked at how accurately its model (had it existed back then) would have tracked the hurricane.
Very accurately, it turns out. Windborne’s predictions aligned neatly with the storm’s actual path, while the National Weather Service’s model was off by hundreds of kilometers. That impressed Khosla Ventures, which led the company’s $15 million Series A funding round earlier this month. “We haven’t seen meaningful innovation in weather since The Weather Channel in the 90s. Yet it’s a $100 billion market that touches essentially every industry,” Sven Strohband, a partner and managing director at Khosla Ventures, told me via email.
With this new funding, Windborne is scaling up its fleet of balloons as it prepares to commercialize. The money will also help Windborne advance its forecasting model, though Dean told me robust data collection is ultimately what will set the company apart. “In any kind of AI industry, whoever has the top benchmark at any given time, it’s going to fluctuate,” Dean said. “What matters is the model plus the unique datasets.”
Unlike Windborne, the tech giants with AI-based weather models — including, most recently, Microsoft — aren’t gathering their own data, instead drawing solely on publicly accessible information from legacy weather agencies.
But these agencies are starting to get into the game, too. The European Centre for Medium-Range Weather Forecasts has already created its own AI-based model, the Artificial Intelligence/Integrated Forecasting System, which it runs in parallel to its traditional model. NOAA, while a bit behind, is also looking to follow suit.
“In the end, we know we can't rely on these big tech companies to just keep developing stuff in good faith to give to us for free,” Kleist told me. Right now, many of the top AI-based weather models are open source. But who knows if that will last? “It's our mission to save lives and property. And we have to figure out how to do some of this development and operationalize it from our side, ourselves,” Kleist said, explaining that NOAA is currently prototyping some of its own AI-based models.
All of these agencies are in the early stages of AI modeling, which is why you likely haven’t noticed weather predictions making a pronounced leap in accuracy as of late. It’s all still considered quite experimental. “Physical models, the pro is we know the underlying assumptions we make. We understand them. We have decades of history of developing them and using them in operational settings,” Kleist told me. AI-based models are much more of a black box, and there’s questions surrounding how well they will perform when it comes to predicting rare weather events, for which there might be little to no historical data for the model to reference.
That hesitation might not last long, though. “To me it’s fairly obvious that most of the forecasts that would actually be used by users in the future will come from machine learning models,” Peter Dueben, head of Earth systems modeling at the European Centre for Medium Range Weather Forecasting, told me. “If you just want to get the weather forecast for the temperature in California tomorrow, then the machine learning model is typically the better choice,” he added.
That increased accuracy is going to matter a lot, not just for the average weather watcher, but also for specific industries and interest groups for whom precise predictions are paramount. “We can tailor the actual models to particular sectors, whether it's agriculture, energy, transportation,” Kleist told me, “and come up with information that's going to be at a very granular, specific level to a particular interest.” Think grid operators or renewable power generators who need to forecast demand or farmers trying to figure out the best time to irrigate their fields or harvest crops.
A major (and perhaps surprising) reason this type of customization is so easy is because once AI-based weather models are trained, they’re actually orders of magnitude cheaper and less computationally intensive to run than traditional models. All of this means, Kleist told me, that AI-based weather models are “going to be fundamentally foundational for what we do in the future, and will open up avenues to things we couldn't have imagined using our current physical-based modeling.”
Log in
To continue reading, log in to your account.
Create a Free Account
To unlock more free articles, please create a free account.
On environmental justice grants, melting glaciers, and Amazon’s carbon credits
Current conditions: Severe thunderstorms are expected across the Mississippi Valley this weekend • Storm Martinho pushed Portugal’s wind power generation to “historic maximums” • It’s 62 degrees Fahrenheit, cloudy, and very quiet at Heathrow Airport outside London, where a large fire at an electricity substation forced the international travel hub to close.
President Trump invoked emergency powers Thursday to expand production of critical minerals and reduce the nation’s reliance on other countries. The executive order relies on the Defense Production Act, which “grants the president powers to ensure the nation’s defense by expanding and expediting the supply of materials and services from the domestic industrial base.”
Former President Biden invoked the act several times during his term, once to accelerate domestic clean energy production, and another time to boost mining and critical minerals for the nation’s large-capacity battery supply chain. Trump’s order calls for identifying “priority projects” for which permits can be expedited, and directs the Department of the Interior to prioritize mineral production and mining as the “primary land uses” of federal lands that are known to contain minerals.
Critical minerals are used in all kinds of clean tech, including solar panels, EV batteries, and wind turbines. Trump’s executive order doesn’t mention these technologies, but says “transportation, infrastructure, defense capabilities, and the next generation of technology rely upon a secure, predictable, and affordable supply of minerals.”
Anonymous current and former staffers at the Environmental Protection Agency have penned an open letter to the American people, slamming the Trump administration’s attacks on climate grants awarded to nonprofits under the Inflation Reduction Act’s Greenhouse Gas Reduction Fund. The letter, published in Environmental Health News, focuses mostly on the grants that were supposed to go toward environmental justice programs, but have since been frozen under the current administration. For example, Climate United was awarded nearly $7 billion to finance clean energy projects in rural, Tribal, and low-income communities.
“It is a waste of taxpayer dollars for the U.S. government to cancel its agreements with grantees and contractors,” the letter states. “It is fraud for the U.S. government to delay payments for services already received. And it is an abuse of power for the Trump administration to block the IRA laws that were mandated by Congress.”
The lives of 2 billion people, or about a quarter of the human population, are threatened by melting glaciers due to climate change. That’s according to UNESCO’s new World Water Development Report, released to correspond with the UN’s first World Day for Glaciers. “As the world warms, glaciers are melting faster than ever, making the water cycle more unpredictable and extreme,” the report says. “And because of glacial retreat, floods, droughts, landslides, and sea-level rise are intensifying, with devastating consequences for people and nature.” Some key stats about the state of the world’s glaciers:
In case you missed it: Amazon has started selling “high-integrity science-based carbon credits” to its suppliers and business customers, as well as companies that have committed to being net-zero by 2040 in line with Amazon’s Climate Pledge, to help them offset their greenhouse gas emissions.
“The voluntary carbon market has been challenged with issues of transparency, credibility, and the availability of high-quality carbon credits, which has led to skepticism about nature and technological carbon removal as an effective tool to combat climate change,” said Kara Hurst, chief sustainability officer at Amazon. “However, the science is clear: We must halt and reverse deforestation and restore millions of miles of forests to slow the worst effects of climate change. We’re using our size and high vetting standards to help promote additional investments in nature, and we are excited to share this new opportunity with companies who are also committed to the difficult work of decarbonizing their operations.”
The Bureau of Land Management is close to approving the environmental review for a transmission line that would connect to BluEarth Renewables’ Lucky Star wind project, Heatmap’s Jael Holzman reports in The Fight. “This is a huge deal,” she says. “For the last two months it has seemed like nothing wind-related could be approved by the Trump administration. But that may be about to change.”
BLM sent local officials an email March 6 with a draft environmental assessment for the transmission line, which is required for the federal government to approve its right-of-way under the National Environmental Policy Act. According to the draft, the entirety of the wind project is sited on private property and “no longer will require access to BLM-administered land.”
The email suggests this draft environmental assessment may soon be available for public comment. BLM’s web page for the transmission line now states an approval granting right-of-way may come as soon as May. BLM last week did something similar with a transmission line that would go to a solar project proposed entirely on private lands. Holzman wonders: “Could private lands become the workaround du jour under Trump?”
Saudi Aramco, the world’s largest oil producer, this week launched a pilot direct air capture unit capable of removing 12 tons of carbon dioxide per year. In 2023 alone, the company’s Scope 1 and Scope 2 emissions totalled 72.6 million metric tons of carbon dioxide equivalent.
If you live in Illinois or Massachusetts, you may yet get your robust electric vehicle infrastructure.
Robust incentive programs to build out electric vehicle charging stations are alive and well — in Illinois, at least. ComEd, a utility provider for the Chicago area, is pushing forward with $100 million worth of rebates to spur the installation of EV chargers in homes, businesses, and public locations around the Windy City. The program follows up a similar $87 million investment a year ago.
Federal dollars, once the most visible source of financial incentives for EVs and EV infrastructure, are critically endangered. Automakers and EV shoppers fear the Trump administration will attack tax credits for purchasing or leasing EVs. Executive orders have already suspended the $5 billion National Electric Vehicle Infrastructure Formula Program, a.k.a. NEVI, which was set up to funnel money to states to build chargers along heavily trafficked corridors. With federal support frozen, it’s increasingly up to the automakers, utilities, and the states — the ones with EV-friendly regimes, at least — to pick up the slack.
Illinois’ investment has been four years in the making. In 2021, the state established an initiative to have a million EVs on its roads by 2030, and ComEd’s new program is a direct outgrowth. The new $100 million investment includes $53 million in rebates for business and public sector EV fleet purchases, $38 million for upgrades necessary to install public and private Level 2 and Level 3 chargers, stations for non-residential customers, and $9 million to residential customers who buy and install home chargers, with rebates of up to $3,750 per charger.
Massachusetts passed similar, sweeping legislation last November. Its bill was aimed to “accelerate clean energy development, improve energy affordability, create an equitable infrastructure siting process, allow for multistate clean energy procurements, promote non-gas heating, expand access to electric vehicles and create jobs and support workers throughout the energy transition.” Amid that list of hifalutin ambition, the state included something interesting and forward-looking: a pilot program of 100 bidirectional chargers meant to demonstrate the power of vehicle-to-grid, vehicle-to-home, and other two-way charging integrations that could help make the grid of the future more resilient.
Many states, blue ones especially, have had EV charging rebates in places for years. Now, with evaporating federal funding for EVs, they have to take over as the primary benefactor for businesses and residents looking to electrify, as well as a financial level to help states reach their public targets for electrification.
Illinois, for example, saw nearly 29,000 more EVs added to its roads in 2024 than 2023, but that growth rate was actually slower than the previous year, which mirrors the national narrative of EV sales continuing to grow, but more slowly than before. In the time of hostile federal government, the state’s goal of jumping from about 130,000 EVs now to a million in 2030 may be out of reach. But making it more affordable for residents and small businesses to take the leap should send the numbers in the right direction, as will a state-backed attempt to create more public EV chargers.
The private sector is trying to juice charger expansion, too. Federal funding or not, the car companies need a robust nationwide charging network to boost public confidence as they roll out more electric offerings. Ionna — the charging station partnership funded by the likes of Hyundai, BMW, General Motors, Honda, Kia, Mercedes-Benz, Stellantis, and Toyota — is opening new chargers at Sheetz gas stations. It promises to open 1,000 new charging bays this year and 30,000 by 2030.
Hyundai, being the number two EV company in America behind much-maligned Tesla, has plenty at stake with this and similar ventures. No surprise, then, that its spokesperson told Automotive Dive that Ionna doesn’t rely on federal dollars and will press on regardless of what happens in Washington. Regardless of the prevailing winds in D.C., Hyundai/Kia is motivated to support a growing national network to boost the sales of models on the market like the Hyundai Ioniq5 and Kia EV6, as well as the company’s many new EVs in the pipeline. They’re not alone. Mercedes-Benz, for example, is building a small supply of branded high-power charging stations so its EV drivers can refill their batteries in Mercedes luxury.
The fate of the federal NEVI dollars is still up in the air. The clearinghouse on this funding shows a state-by-state patchwork. More than a dozen states have some NEVI-funded chargers operational, but a few have gotten no further than having their plans for fiscal year 2024 approved. Only Rhode Island has fully built out its planned network. It’s possible that monies already allocated will go out, despite the administration’s attempt to kill the program.
In the meantime, Tesla’s Supercharger network is still king of the hill, and with a growing number of its stations now open to EVs from other brands (and a growing number of brands building their new EVs with the Tesla NACS charging port), Superchargers will be the most convenient option for lots of electric drivers on road trips. Unless the alternatives can become far more widespread and reliable, that is.
The increasing state and private focus on building chargers is good for all EV drivers, starting with those who haven’t gone in on an electric car yet and are still worried about range or charger wait times on the road to their destination. It is also, by the way, good news for the growing number of EV folks looking to avoid Elon Musk at all cost.
From Kansas to Brooklyn, the fire is turning battery skeptics into outright opponents.
The symbol of the American battery backlash can be found in the tiny town of Halstead, Kansas.
Angry residents protesting a large storage project proposed by Boston developer Concurrent LLC have begun brandishing flashy yard signs picturing the Moss Landing battery plant blaze, all while freaking out local officials with their intensity. The modern storage project bears little if any resemblance to the Moss Landing facility, which uses older technology,, but that hasn’t calmed down anxious locals or stopped news stations from replaying footage of the blaze in their coverage of the conflict.
The city of Halstead, under pressure from these locals, is now developing a battery storage zoning ordinance – and explicitly saying this will not mean a project “has been formally approved or can be built in the city.” The backlash is now so intense that Halstead’s mayor Dennis Travis has taken to fighting back against criticism on Facebook, writing in a series of posts about individuals in his community “trying to rule by MOB mentality, pushing out false information and intimidating” volunteers working for the city. “I’m exercising MY First Amendment Right and well, if you don’t like it you can kiss my grits,” he wrote. Other posts shared information on the financial benefits of building battery storage and facts to dispel worries about battery fires. “You might want to close your eyes and wish this technology away but that is not going to happen,” another post declared. “Isn’t it better to be able to regulate it in our community?”
What’s happening in Halstead is a sign of a slow-spreading public relations wildfire that’s nudging communities that were already skeptical of battery storage over the edge into outright opposition. We’re not seeing any evidence that communities are transforming from supportive to hostile – but we are seeing new areas that were predisposed to dislike battery storage grow more aggressive and aghast at the idea of new projects.
Heatmap Pro data actually tells the story quite neatly: Halstead is located in Harvey County, a high risk area for developers that already has a restrictive ordinance banning all large-scale solar and wind development. There’s nothing about battery storage on the books yet, but our own opinion poll modeling shows that individuals in this county are more likely to oppose battery storage than renewable energy.
We’re seeing this phenomenon play out elsewhere as well. Take Fannin County, Texas, where residents have begun brandishing the example of Moss Landing to rail against an Engie battery storage project, and our modeling similarly shows an intense hostility to battery projects. The same can be said about Brooklyn, New York, where anti-battery concerns are far higher in our polling forecasts – and opposition to battery storage on the ground is gaining steam.